Generative AI with Python
Build LLMs, RAG & Agents in Python
Created by Bert Gollnick
Explore hands-on techniques for building and deploying large language model applications using Python. Move from setting up your development environment to advanced topics like retrieval-augmented generation, vector search, and multi-agent systems. Learn to fine-tune models and integrate guardrails for safe, production-ready solutions.
Packt | Sep 2025 | 620 min
What You Will Learn
You will work through practical coding exercises and real-world projects that introduce each concept in a clear, step-by-step manner. With a focus on hands-on experience, you will build, test, and refine your own LLM pipelines, retrieval systems, and agentic workflows, gaining skills you can immediately apply to real applications.
Key Features
- Set up secure Python environments and manage API credentials with confidence
- Interact with multiple LLM providers and optimize model performance in code
- Design and implement prompt templates, LLM chains, and structured outputs
Target Audience
Ideal for software engineers, data scientists, and technical architects who are comfortable with Python and want to build real-world LLM solutions. If you have basic experience with scripting, Git, and JSON, you will be able to follow along and deepen your expertise in deploying advanced AI systems.
